Transformers
GGUF
English
code
hpc
parallel
axonn
imatrix
conversational
nicoboss mradermacher commited on
Commit
c4fc368
·
verified ·
0 Parent(s):

Duplicate from mradermacher/hpc-coder-v2-16b-i1-GGUF

Browse files

Co-authored-by: team mradermacher <[email protected]>

.gitattributes ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ hpc-coder-v2-16b.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ hpc-coder-v2-16b.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
38
+ hpc-coder-v2-16b.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
39
+ hpc-coder-v2-16b.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
40
+ hpc-coder-v2-16b.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
41
+ hpc-coder-v2-16b.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
42
+ hpc-coder-v2-16b.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
43
+ hpc-coder-v2-16b.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
44
+ hpc-coder-v2-16b.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
45
+ hpc-coder-v2-16b.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
46
+ hpc-coder-v2-16b.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text
47
+ hpc-coder-v2-16b.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
48
+ hpc-coder-v2-16b.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
49
+ hpc-coder-v2-16b.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
50
+ hpc-coder-v2-16b.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
51
+ hpc-coder-v2-16b.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
52
+ hpc-coder-v2-16b.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
53
+ hpc-coder-v2-16b.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
54
+ hpc-coder-v2-16b.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
55
+ hpc-coder-v2-16b.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
56
+ hpc-coder-v2-16b.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
57
+ hpc-coder-v2-16b.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
58
+ hpc-coder-v2-16b.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
59
+ hpc-coder-v2-16b.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: hpcgroup/hpc-coder-v2-16b
3
+ datasets:
4
+ - hpcgroup/hpc-instruct
5
+ - ise-uiuc/Magicoder-OSS-Instruct-75K
6
+ - nickrosh/Evol-Instruct-Code-80k-v1
7
+ language:
8
+ - en
9
+ library_name: transformers
10
+ quantized_by: mradermacher
11
+ tags:
12
+ - code
13
+ - hpc
14
+ - parallel
15
+ - axonn
16
+ ---
17
+ ## About
18
+
19
+ <!-- ### quantize_version: 2 -->
20
+ <!-- ### output_tensor_quantised: 1 -->
21
+ <!-- ### convert_type: hf -->
22
+ <!-- ### vocab_type: -->
23
+ <!-- ### tags: nicoboss -->
24
+ weighted/imatrix quants of https://huggingface.co/hpcgroup/hpc-coder-v2-16b
25
+
26
+ <!-- provided-files -->
27
+ static quants are available at https://huggingface.co/mradermacher/hpc-coder-v2-16b-GGUF
28
+ ## Usage
29
+
30
+ If you are unsure how to use GGUF files, refer to one of [TheBloke's
31
+ READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
32
+ more details, including on how to concatenate multi-part files.
33
+
34
+ ## Provided Quants
35
+
36
+ (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
37
+
38
+ | Link | Type | Size/GB | Notes |
39
+ |:-----|:-----|--------:|:------|
40
+ | [GGUF](https://huggingface.co/mradermacher/hpc-coder-v2-16b-i1-GGUF/resolve/main/hpc-coder-v2-16b.i1-IQ1_S.gguf) | i1-IQ1_S | 5.1 | for the desperate |
41
+ | [GGUF](https://huggingface.co/mradermacher/hpc-coder-v2-16b-i1-GGUF/resolve/main/hpc-coder-v2-16b.i1-IQ1_M.gguf) | i1-IQ1_M | 5.3 | mostly desperate |
42
+ | [GGUF](https://huggingface.co/mradermacher/hpc-coder-v2-16b-i1-GGUF/resolve/main/hpc-coder-v2-16b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 5.7 | |
43
+ | [GGUF](https://huggingface.co/mradermacher/hpc-coder-v2-16b-i1-GGUF/resolve/main/hpc-coder-v2-16b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 6.1 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/hpc-coder-v2-16b-i1-GGUF/resolve/main/hpc-coder-v2-16b.i1-IQ2_S.gguf) | i1-IQ2_S | 6.1 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/hpc-coder-v2-16b-i1-GGUF/resolve/main/hpc-coder-v2-16b.i1-IQ2_M.gguf) | i1-IQ2_M | 6.4 | |
46
+ | [GGUF](https://huggingface.co/mradermacher/hpc-coder-v2-16b-i1-GGUF/resolve/main/hpc-coder-v2-16b.i1-Q2_K.gguf) | i1-Q2_K | 6.5 | IQ3_XXS probably better |
47
+ | [GGUF](https://huggingface.co/mradermacher/hpc-coder-v2-16b-i1-GGUF/resolve/main/hpc-coder-v2-16b.i1-Q2_K_S.gguf) | i1-Q2_K_S | 6.6 | very low quality |
48
+ | [GGUF](https://huggingface.co/mradermacher/hpc-coder-v2-16b-i1-GGUF/resolve/main/hpc-coder-v2-16b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 7.1 | lower quality |
49
+ | [GGUF](https://huggingface.co/mradermacher/hpc-coder-v2-16b-i1-GGUF/resolve/main/hpc-coder-v2-16b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 7.2 | |
50
+ | [GGUF](https://huggingface.co/mradermacher/hpc-coder-v2-16b-i1-GGUF/resolve/main/hpc-coder-v2-16b.i1-IQ3_S.gguf) | i1-IQ3_S | 7.6 | beats Q3_K* |
51
+ | [GGUF](https://huggingface.co/mradermacher/hpc-coder-v2-16b-i1-GGUF/resolve/main/hpc-coder-v2-16b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 7.6 | IQ3_XS probably better |
52
+ | [GGUF](https://huggingface.co/mradermacher/hpc-coder-v2-16b-i1-GGUF/resolve/main/hpc-coder-v2-16b.i1-IQ3_M.gguf) | i1-IQ3_M | 7.7 | |
53
+ | [GGUF](https://huggingface.co/mradermacher/hpc-coder-v2-16b-i1-GGUF/resolve/main/hpc-coder-v2-16b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 8.2 | IQ3_S probably better |
54
+ | [GGUF](https://huggingface.co/mradermacher/hpc-coder-v2-16b-i1-GGUF/resolve/main/hpc-coder-v2-16b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 8.6 | IQ3_M probably better |
55
+ | [GGUF](https://huggingface.co/mradermacher/hpc-coder-v2-16b-i1-GGUF/resolve/main/hpc-coder-v2-16b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 8.7 | |
56
+ | [GGUF](https://huggingface.co/mradermacher/hpc-coder-v2-16b-i1-GGUF/resolve/main/hpc-coder-v2-16b.i1-IQ4_NL.gguf) | i1-IQ4_NL | 9.0 | prefer IQ4_XS |
57
+ | [GGUF](https://huggingface.co/mradermacher/hpc-coder-v2-16b-i1-GGUF/resolve/main/hpc-coder-v2-16b.i1-Q4_0.gguf) | i1-Q4_0 | 9.0 | fast, low quality |
58
+ | [GGUF](https://huggingface.co/mradermacher/hpc-coder-v2-16b-i1-GGUF/resolve/main/hpc-coder-v2-16b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 9.6 | optimal size/speed/quality |
59
+ | [GGUF](https://huggingface.co/mradermacher/hpc-coder-v2-16b-i1-GGUF/resolve/main/hpc-coder-v2-16b.i1-Q4_1.gguf) | i1-Q4_1 | 10.0 | |
60
+ | [GGUF](https://huggingface.co/mradermacher/hpc-coder-v2-16b-i1-GGUF/resolve/main/hpc-coder-v2-16b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 10.5 | fast, recommended |
61
+ | [GGUF](https://huggingface.co/mradermacher/hpc-coder-v2-16b-i1-GGUF/resolve/main/hpc-coder-v2-16b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 11.2 | |
62
+ | [GGUF](https://huggingface.co/mradermacher/hpc-coder-v2-16b-i1-GGUF/resolve/main/hpc-coder-v2-16b.i1-Q5_K_M.gguf) | i1-Q5_K_M | 12.0 | |
63
+ | [GGUF](https://huggingface.co/mradermacher/hpc-coder-v2-16b-i1-GGUF/resolve/main/hpc-coder-v2-16b.i1-Q6_K.gguf) | i1-Q6_K | 14.2 | practically like static Q6_K |
64
+
65
+ Here is a handy graph by ikawrakow comparing some lower-quality quant
66
+ types (lower is better):
67
+
68
+ ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
69
+
70
+ And here are Artefact2's thoughts on the matter:
71
+ https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
72
+
73
+ ## FAQ / Model Request
74
+
75
+ See https://huggingface.co/mradermacher/model_requests for some answers to
76
+ questions you might have and/or if you want some other model quantized.
77
+
78
+ ## Thanks
79
+
80
+ I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
81
+ me use its servers and providing upgrades to my workstation to enable
82
+ this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
83
+
84
+ <!-- end -->
hpc-coder-v2-16b.i1-IQ1_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c742de5aa66eb28412413660907c83c97256087b25523f52f51bf469fabca93
3
+ size 5236566592
hpc-coder-v2-16b.i1-IQ1_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9deda40f9308591dfa941dc657b29b447d3b40871b3885d2af889a27aa7f9ccd
3
+ size 4994133568
hpc-coder-v2-16b.i1-IQ2_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:399713e0238f8897ba2378c9d3255788aad10524c186d75cdbdbc7c4e802bbff
3
+ size 6328458816
hpc-coder-v2-16b.i1-IQ2_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34f488e57d32f496c9d64128baee1e68f114f5c0cc1f8828d4dcca40f3f1f86d
3
+ size 6005214784
hpc-coder-v2-16b.i1-IQ2_XS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a553b0953c7e108197f903a4356624d9586980142f0319309336ef45345e230
3
+ size 5967404608
hpc-coder-v2-16b.i1-IQ2_XXS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:997207fadd34968ff1ac0c1e9fec04fdcea56938b9cf5d7959cc3c6661414c62
3
+ size 5640621632
hpc-coder-v2-16b.i1-IQ3_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b637e74a3c38c5e9bf09d8d1d34513c2b70b987e268ba4dd8f997521ba38d5ce
3
+ size 7553177152
hpc-coder-v2-16b.i1-IQ3_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40ee6debbdeb17bdbbde34520cc77c433f2aa425eeb6d3d77f3f7ed004609535
3
+ size 7487665728
hpc-coder-v2-16b.i1-IQ3_XS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8b178a4db69f29846344c4a7687919ba1a15f3b400035af05676ddd38d699cb
3
+ size 7122859584
hpc-coder-v2-16b.i1-IQ3_XXS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efbd2276723cecb2a6fc77762996983b0cf526d4d612e6f211a62517b034e8a8
3
+ size 6964059712
hpc-coder-v2-16b.i1-IQ4_NL.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a41127456a939f6a1b391817ff66a47ba3733eb4100fa548d41f020d88db659
3
+ size 8905112128
hpc-coder-v2-16b.i1-IQ4_XS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89f8f9d7a4b0ba0afbd5f52cb5f19afeaaa658892f3641edf27fcf024ddc6635
3
+ size 8571595328
hpc-coder-v2-16b.i1-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:280f331aa227143d5ac3f35536638ceac595c15d0a6c2183d4164c279f03e1cf
3
+ size 6430466624
hpc-coder-v2-16b.i1-Q2_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2176382e79028cc8d0e4e2dc4fb60cdbde5c5d1e86d8921097c43c39d767bfca
3
+ size 6455378496
hpc-coder-v2-16b.i1-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5141d3f571f8c5d4558070456909ce0ffd0cdb733fac897c8b6b9e0ea52b1c84
3
+ size 8459400768
hpc-coder-v2-16b.i1-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5060726f81ce126d297c42c84c08da62fe8d6be8f4b0f5740d4263a1cad28d4b
3
+ size 8126608960
hpc-coder-v2-16b.i1-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b11684a790d3967368280515b65a1ad09d4e06f3bcea44af2978609dc500c679
3
+ size 7487665728
hpc-coder-v2-16b.i1-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12cd3bc255aa5e80861570b1278cad8fe8d0e9957265b028b110a160b5b3f814
3
+ size 8930302528
hpc-coder-v2-16b.i1-Q4_1.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab7eab67f57b6192f020d1ba1a7528aee0068e6be49240753bea0f73cc1f7a5d
3
+ size 9873439296
hpc-coder-v2-16b.i1-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7500acf96822e781f74d30d6dfd60ff702a5f7dc6081edbe3bed622a54056c0
3
+ size 10364418624
hpc-coder-v2-16b.i1-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bd985f22193f74c93c3cd69cdc18d0a139028f5d7f6a5b1b503dfe2e0c3345a
3
+ size 9533610560
hpc-coder-v2-16b.i1-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94a38c35fd62ffc2be3d0f496010f3b59f868b4b8dce3070502a47035a387192
3
+ size 11851315776
hpc-coder-v2-16b.i1-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78de6094f1dfb7cbf4e9911218f02eb83d0f7d56056bdc4345aa7fd01a827111
3
+ size 11143060032
hpc-coder-v2-16b.i1-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44fc5fa59a7031261d4a4e30b65cc6a9ad25f363da252f4b611c89fcb1810d70
3
+ size 14066974272